Learners in agent interaction became locked in lower-order self-transition loops (e.g., Understand z = 49.08, Application z = 51.48) and rarely transitioned spontaneously to higher-order cognition¶

Claim · All claims
Evidence · 1 study · causal r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? All cognitive behaviors except UN showed significant self-transitions in student-agent interaction, with strong lower-order loops indicating learners stayed in routine information processing. → Li 2026

Evidence¶

Li 2026¶

Li, X., Liu, Z., Jiang, S., Chen, J., & Chen, W. (2026). The impact of an LLM-based educational agent on learning achievement, cognitive dynamics, and student perceptions in computer science education. International Journal of STEM Education. https://doi.org/10.1186/s40594-026-00641-y

q2 · i? · causal · r2

LSA of student-agent interaction logs shows strong self-transition loops in lower-order states — "Understand (z = 49.08) and Application (z = 51.48)" — which the authors interpret as learners locked in routine processing rather than progressing to Analysis or Creating.

"strong self-transition loops were observed within lower-order states, such as Understand (z = 49.08) and Application (z = 51.48), indicating that learners tend to become "locked" in routine information processing rather than progressing to Analysis or Creating"

Discussion¶

Related Claims¶

• Student-agent interaction produced far more help-seeking but a non-uniform cognitive distribution dominated by lower-order engagement (54.52%), unlike the balanced distribution of student-instructor interaction — a broader claim this one bears on
• Student-agent interaction featured a significant Query-Evaluation-Query verification loop (RM-QR-EA), distinct from the linear QR-UN path of student-instructor interaction — related
• High CT students used the AICA for code understanding and debugging while low CT students used it for direct answer retrieval — related